TY  - JOUR
VL  - 167
AV  - none
Y1  - 2020///
KW  - Convolutional neural networks; Deep learning; Image segmentation; Learning systems; Marine pollution; Marine radar; Oil spills; Semantics; Synthetic aperture radar; Transfer learning
KW  -  Conventional machines; Detection and discriminations; Oil spill detection; Overall accuracies; Segmentation masks; Segmentation models; Semantic segmentation; Synthetic aperture radar (SAR) images
KW  -  Learning algorithms
KW  -  algorithm; detection method; image analysis; machine learning; model; satellite imagery; segmentation; synthetic aperture radar
A1  - Temitope Yekeen, S.
A1  - Balogun, A.L.
A1  - Wan Yusof, K.B.
SP  - 190
PB  - Elsevier B.V.
EP  - 200
UR  - https://www.scopus.com/inward/record.uri?eid=2-s2.0-85088631447&doi=10.1016%2fj.isprsjprs.2020.07.011&partnerID=40&md5=bdfc287eb4cd977e889cb0d756b0153a
N2  - The visual similarity of oil slick and other elements, known as look-alike, affects the reliability of synthetic aperture radar (SAR) images for marine oil spill detection. So far, detection and discrimination of oil spill and look-alike are still limited to the use of traditional machine learning algorithms and semantic segmentation deep learning models with limited accuracy. Thus, this study developed a novel deep learning oil spill detection model using computer vision instance segmentation Mask-Region-based Convolutional Neural Network (Mask R-CNN) model. The model training was conducted using transfer learning on the ResNet 101 on COCO as backbone in combination with Feature Pyramid Network (FPN) architecture for feature extraction at 30 epochs with 0.001 learning rate. Testing of the model was conducted using the least training and validation loss value on the withheld testing images. The model's performance was evaluated using precision, recall, specificity, IoU, F1-measure and overall accuracy values. Ship detection and segmentation had the highest performance with overall accuracy of 98.3. The model equally showed a higher accuracy for oil spill and look-alike detection and segmentation although oil spill detection outperformed look-alike with overall accuracy values of 96.6 and 91.0 respectively. The study concluded that the deep learning instance segmentation model performs better than conventional machine learning models and deep learning semantic segmentation models in detection and segmentation. © 2020 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS)
ID  - scholars12791
N1  - cited By 81
TI  - A novel deep learning instance segmentation model for automated marine oil spill detection
SN  - 09242716
JF  - ISPRS Journal of Photogrammetry and Remote Sensing
ER  -